Site memory

Site memory is the structured context your enterprise hands to agents — page map, workflows, business policies, UI guidance, per-page state. The point: agents stop screenshotting their way through your site.

This is not the agent's own memory. Conversation history belongs to the agent. Site memory belongs to you.

Provide it once

client.provideSiteMemory({
  siteMap: {
    pages: [
      { path: '/', name: 'Home', purpose: 'Featured products' },
      { path: '/cart', name: 'Cart', availableActions: ['proceedToCheckout'] },
      { path: '/checkout', name: 'Checkout', prerequisites: ['Cart must not be empty'] },
    ],
    navigation: { flow: 'Home → Cart → Checkout', pattern: 'linear' },
  },
  workflows: {
    purchase: {
      steps: [
        { step: 1, action: 'Add items to cart' },
        { step: 2, action: 'Review cart' },
        { step: 3, action: 'Checkout' },
      ],
      notes: 'User confirmation required at step 3.',
    },
  },
  policies: {
    shipping: 'Free over $50',
    returns: '30-day window',
  },
  uiGuidance: {
    addToCart: { selector: '.add-to-cart-btn', behavior: 'Click to add 1 unit' },
    checkout: { selector: '#proceed-checkout', location: 'Right sidebar of /cart' },
  },
})

provideSiteMemory merges keys, so partial updates do not nuke siblings. Use client.siteMemory.update('policies.shipping', '...') to overwrite a single dot-path.

Per-page context

Pages with dynamic state (a checkout that knows the cart total, a search page that knows the active filter) can override their slice without rewriting the whole snapshot.

client.provideForPage({
  path: '/checkout',
  payload: {
    currentStep: 'order-review',
    estimatedTotal: 49.99,
    requiredFields: ['shipping-address', 'payment-method'],
  },
})

Page contexts ride alongside the global snapshot. WebMCP and well-known clients can pull pageContexts['/checkout'] to read the live state.

Four delivery channels

Different agent classes consume site memory differently. The SDK ships all four channels — pick the ones that match the agents you care about.

Channel	Best for	API
WebMCP synthetic tool	WebMCP-native agents	createWebMcpContextTool({ getSnapshot })
<meta> + JSON-LD	DOM agents, search engines	client.installMemoryDelivery({ metaTags: true })
Visual overlay	Screenshot agents	client.installMemoryDelivery({ overlay: true })
/.well-known/agent-context.json	Anything, no SDK	serializeWellKnownContext({ snapshot }) on the host

The well-known endpoint is the universal fallback — like robots.txt for AI agents. Agentronics serves it through the gateway; production hosts proxy from their domain.

Gateway sync

Site memory authored in the dashboard syncs into the browser SDK on demand:

await client.syncSiteMemory()

The SDK keeps an ETag, so subsequent syncs are 304s with no payload.

Traces

Every provide, update, provideForPage, and gateway/well-known sync emits a memory.updated trace tagged with metadata.kind === 'site'. Reads through siteMemory.get() and the WebMCP tool emit memory.accessed. Use those to see exactly what agents pull from you.